TY - CHAP U1 - Konferenzveröffentlichung A1 - Laube, Pascal A1 - Franz, Matthias O. A1 - Umlauf, Georg T1 - Evaluation of features for SVM-based classification of geometric primitives in point clouds T2 - Proceedings of the Fifteenth IAPR International Conference on Machine Vision Applications (MVA), 8-12 May 2017, Nagoya, Japan N2 - In the reverse engineering process one has to classify parts of point clouds with the correct type of geometric primitive. Features based on different geometric properties like point relations, normals, and curvature information can be used, to train classifiers like Support Vector Machines (SVM). These geometric features are estimated in the local neighborhood of a point of the point cloud. The multitude of different features makes an in-depth comparison necessary. In this work we evaluate 23 features for the classification of geometric primitives in point clouds. Their performance is evaluated on SVMs when used to classify geometric primitives in simulated and real laser scanned point clouds. We also introduce a normalization of point cloud density to improve classification generalization. Y1 - 2017 UN - https://nbn-resolving.org/urn:nbn:de:bsz:kon4-opus4-18493 SN - 978-4-9011-2216-0 SB - 978-4-9011-2216-0 U6 - https://doi.org/10.23919/MVA.2017.7986776 DO - https://doi.org/10.23919/MVA.2017.7986776 SP - 59 EP - 62 S1 - 4 Seiten PB - IEEE ER -